Search Results for author:
Found 9 papers, 6 papers with code
aiXcoder-7B: A Lightweight and Effective Large Language Model for Code Completion
In this paper, we propose a lightweight and effective LLM for code completion named aiXcoder-7B.
FAN: Fourier Analysis Networks
Despite the remarkable success achieved by neural networks, particularly those represented by MLP and Transformer, we reveal that they exhibit potential flaws in the modeling and reasoning of periodicity, i. e., they tend to memorize the periodic data rather than genuinely understanding the underlying principles of periodicity.
Dual Latent State Learning: Exploiting Regional Network Similarities for QoS Prediction
Individual objects, whether users or services, within a specific region often exhibit similar network states due to their shared origin from the same city or autonomous system (AS).
Self-Edit: Fault-Aware Code Editor for Code Generation
Inspired by the process of human programming, we propose a generate-and-edit approach named Self-Edit that utilizes execution results of the generated code from LLMs to improve the code quality on the competitive programming task.
Implant Global and Local Hierarchy Information to Sequence based Code Representation Models
Furthermore, we propose the Hierarchy Transformer (HiT), a simple but effective sequence model to incorporate the complete hierarchical embeddings of source code into a Transformer model.
CodeEditor: Learning to Edit Source Code with Pre-trained Models
Pre-trained models are first pre-trained with pre-training tasks and fine-tuned with the code editing task.
Learning Program Representations with a Tree-Structured Transformer
Learning vector representations for programs is a critical step in applying deep learning techniques for program understanding tasks.
What does Transformer learn about source code?
In the field of source code processing, the transformer-based representation models have shown great powerfulness and have achieved state-of-the-art (SOTA) performance in many tasks.
Learning to Represent Programs with Heterogeneous Graphs
To address the information of node and edge types, we bring the idea of heterogeneous graphs to learning on source code and present a new formula of building heterogeneous program graphs from ASTs with additional type information for nodes and edges.
